Any2Graph: Deep End-to-End Supervised Graph Prediction with an Optimal Transport Loss

Abstract

We propose Any2graph, a generic framework for end-to-end Supervised Graph Prediction (SGP) i.e. a deep learning model that predicts an entire graph for any kind of input. The framework is built on a novel Optimal Transport loss, the Partially-Masked Fused Gromov-Wasserstein, that exhibits all necessary properties (permutation invariance, differentiability and scalability) and is designed to handle any-sized graphs. Numerical experiments showcase the versatility of the approach that outperform existing competitors on a novel challenging synthetic dataset and a variety of real-world tasks such as map construction from satellite image (Sat2Graph) or molecule prediction from fingerprint (Fingerprint2Graph).

PDF NeurIPS OpenReview Semantic Scholar

Cite

Text

Krzakala et al. "Any2Graph: Deep End-to-End Supervised Graph Prediction with an Optimal Transport Loss." Neural Information Processing Systems, 2024. doi:10.52202/079017-3221

Markdown

[Krzakala et al. "Any2Graph: Deep End-to-End Supervised Graph Prediction with an Optimal Transport Loss." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/krzakala2024neurips-any2graph/) doi:10.52202/079017-3221

BibTeX

@inproceedings{krzakala2024neurips-any2graph,
  title     = {{Any2Graph: Deep End-to-End Supervised Graph Prediction with an Optimal Transport Loss}},
  author    = {Krzakala, Paul and Yang, Junjie and Flamary, Rémi and d'Alché-Buc, Florence and Laclau, Charlotte and Labeau, Matthieu},
  booktitle = {Neural Information Processing Systems},
  year      = {2024},
  doi       = {10.52202/079017-3221},
  url       = {https://mlanthology.org/neurips/2024/krzakala2024neurips-any2graph/}
}